Robust and Explainable Detector of Time Series Anomaly via Augmenting Multiclass Pseudo-Anomalies

TL;DR

RedLamp introduces a robust, explainable time series anomaly detection method that uses diverse data augmentation to generate multiclass pseudo-anomalies, improving detection accuracy and handling contaminated training data.

Contribution

The paper proposes RedLamp, a novel approach employing multiclass pseudo-anomalies and soft labels to enhance robustness and explainability in time series anomaly detection.

Findings

RedLamp outperforms existing methods in anomaly detection accuracy.

It demonstrates robustness against contaminated training data.

The learned latent space is inherently explainable.

Abstract

Unsupervised anomaly detection in time series has been a pivotal research area for decades. Current mainstream approaches focus on learning normality, on the assumption that all or most of the samples in the training set are normal. However, anomalies in the training set (i.e., anomaly contamination) can be misleading. Recent studies employ data augmentation to generate pseudo-anomalies and learn the boundary separating the training samples from the augmented samples. Although this approach mitigates anomaly contamination if augmented samples mimic unseen real anomalies, it suffers from several limitations. (1) Covering a wide range of time series anomalies is challenging. (2) It disregards augmented samples that resemble normal samples (i.e., false anomalies). (3) It places too much trust in the labels of training and augmented samples. In response, we propose RedLamp, which employs diverse data augmentations to generate multiclass pseudo-anomalies and learns the multiclass boundary. Such multiclass pseudo-anomalies cover a wide variety of time series anomalies. We conduct multiclass classification using soft labels, which prevents the model from being overconfident and ensures its robustness against contaminated/false anomalies. The learned latent space is inherently explainable as it is trained to separate pseudo-anomalies into multiclasses. Extensive experiments demonstrate the effectiveness of RedLamp in anomaly detection and its robustness against anomaly contamination.